Aryaman Arora

Identifiers

• name variant Aryaman Arora 0.60 · backfill

Papers (6)

1. The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment cs.CL · 2026 · author #3
2. PreFT: Prefill-only finetuning for efficient inference cs.LG · 2026 · author #2
3. ADAG: Automatically Describing Attribution Graphs cs.CL · 2026 · author #1
4. Verbalizing LLMs' assumptions to explain and control sycophancy cs.CL · 2026 · author #6
5. Language Model Circuits Are Sparse in the Neuron Basis cs.CL · 2026 · author #1
6. Localizing Model Behavior with Path Patching cs.LG · 2023 · author #4

Mentions

• 2601.22594 #1 · arxiv_oai · confidence 0.70 Aryaman Arora
• 2606.06667 #3 · arxiv_oai · confidence 0.70 Aryaman Arora
• 2304.05969 #4 · arxiv_oai · confidence 0.70 Aryaman Arora

Frequent Coauthors

• Zhengxuan Wu 4 shared papers
• Dan Jurafsky 2 shared papers
• Jacob Steinhardt 2 shared papers
• Sarah Schwettmann 2 shared papers
• Andrew Lanpouthakoun 1 shared papers
• Ben Keigwin 1 shared papers
• Chris MacLeod 1 shared papers
• Christopher Potts 1 shared papers
• David Bau 1 shared papers
• Desmond Ong 1 shared papers
• Dhruv Pai 1 shared papers
• Diyi Yang 1 shared papers
• Humishka Zope 1 shared papers
• Isabel Sieh 1 shared papers
• Jared Moore 1 shared papers
• Jiachen Zhao 1 shared papers
• Lucas Sato 1 shared papers
• Lujain Ibrahim 1 shared papers
• Myra Cheng 1 shared papers
• Nicholas Goldowsky-Dill 1 shared papers